Preferences API

Manage user AI mode preferences. AI modes control model selection, temperature, and behavior across the platform. Modes can be set globally or per-workspace. Available modes: economy, balanced, quality, max, speed, and custom. All endpoints require JWT authentication.

Base path: /api/v2/preferences

GET/api/v2/preferences/ai-modeAuthenticated

Get the current AI mode for the authenticated user. Optionally scoped to a workspace.

Query Parameters

workspaceIdstring

UUID of the workspace. Returns workspace-specific mode if set, otherwise global mode.

Request

cURL

curl -X GET "https://api.lvng.ai/api/v2/preferences/ai-mode" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response 200

{
  "success": true,
  "mode": {
    "name": "balanced",
    "model": "claude-sonnet",
    "temperature": 0.7,
    "maxTokens": 4096,
    "description": "Good balance of quality and speed"
  }
}

PATCH/api/v2/preferences/ai-modeAuthenticated

Set the AI mode for the authenticated user. Can be set globally or per-workspace.

Body Parameters

modestringrequired

Mode name: "economy", "balanced", "quality", "max", "speed", or "custom".

workspaceIdstring

UUID of the workspace to set mode for. Omit for global setting.

customConfigobject

Custom configuration when mode is "custom". Allows setting model, temperature, etc.

Request

cURL

curl -X PATCH "https://api.lvng.ai/api/v2/preferences/ai-mode" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

Response 200

{
  "success": true,
  "mode": {
    "name": "quality",
    "model": "claude-opus",
    "temperature": 0.5,
    "maxTokens": 8192,
    "description": "Maximum quality, slower responses"
  }
}

GET/api/v2/preferences/ai-modesAuthenticated

List all available AI modes with their configurations.

Request

cURL

curl -X GET "https://api.lvng.ai/api/v2/preferences/ai-modes" \
  -H "Authorization: Bearer YOUR_API_KEY"

Response 200

{
  "success": true,
  "modes": [
    {
      "name": "economy",
      "model": "claude-haiku",
      "temperature": 0.7,
      "maxTokens": 2048,
      "description": "Fast and affordable for simple tasks"
    },
    {
      "name": "balanced",
      "model": "claude-sonnet",
      "temperature": 0.7,
      "maxTokens": 4096,
      "description": "Good balance of quality and speed"
    },
    {
      "name": "quality",
      "model": "claude-opus",
      "temperature": 0.5,
      "maxTokens": 8192,
      "description": "Maximum quality, slower responses"
    },
    {
      "name": "max",
      "model": "claude-opus",
      "temperature": 0.3,
      "maxTokens": 16384,
      "description": "Maximum capability with extended context"
    },
    {
      "name": "speed",
      "model": "claude-haiku",
      "temperature": 0.9,
      "maxTokens": 1024,
      "description": "Fastest possible responses"
    },
    {
      "name": "custom",
      "model": "configurable",
      "temperature": "configurable",
      "maxTokens": "configurable",
      "description": "Custom configuration"
    }
  ]
}